Centre for Vision, Speech and Signal Processing, Department of Electrical and Electronic Engineering, University of Surrey, Guildford, GU2 7XH, United Kingdom.
Department of Medical Physics and Biomedical Engineering, University College London, London, WC1E 6BT, United Kingdom.
Phys Med Biol. 2021 May 14;66(10). doi: 10.1088/1361-6560/abf1fd.
A Machine Learning approach to the problem of calculating the proton paths inside a scanned object in proton Computed Tomography is presented. The method is developed in order to mitigate the loss in both spatial resolution and quantitative integrity of the reconstructed images caused by multiple Coulomb scattering of protons traversing the matter. Two Machine Learning models were used: a forward neural network (NN) and the XGBoost method. A heuristic approach, based on track averaging was also implemented in order to evaluate the accuracy limits on track calculation, imposed by the statistical nature of the scattering. Synthetic data from anthropomorphic voxelized phantoms, generated by the Monte Carlo (MC) Geant4 code, were utilized to train the models and evaluate their accuracy, in comparison to a widely used analytical method that is based on likelihood maximization and Fermi-Eyges scattering model. Both NN and XGBoost model were found to perform very close or at the accuracy limit, further improving the accuracy of the analytical method (by 12% in the typical case of 200 MeV protons on 20 cm of water object), especially for protons scattered at large angles. Inclusion of the material information along the path in terms of radiation length did not show improvement in accuracy for the phantoms simulated in the study. A NN was also constructed to predict the error in path calculation, thus enabling a criterion to filter out proton events that may have a negative effect on the quality of the reconstructed image. By parametrizing a large set of synthetic data, the Machine Learning models were proved capable to bring-in an indirect and time efficient way-the accuracy of the MC method into the problem of proton tracking.
提出了一种机器学习方法来解决质子计算机断层扫描中计算扫描物体内部质子路径的问题。该方法的开发是为了减轻质子在穿过物质时多次库仑散射导致的重建图像空间分辨率和定量完整性的损失。使用了两种机器学习模型：前馈神经网络（NN）和 XGBoost 方法。还实现了一种基于轨迹平均的启发式方法，以便评估由于散射的统计性质对轨迹计算的准确性限制。利用蒙特卡罗（MC）Geant4 代码生成的人体化体素化体模的合成数据来训练模型并评估其准确性，与基于似然最大化和费米-埃格斯散射模型的广泛使用的分析方法进行比较。NN 和 XGBoost 模型都被发现表现非常接近或达到准确性限制，进一步提高了分析方法的准确性（在典型情况下，对于 200 MeV 质子在 20 cm 水物体上，提高了 12%），特别是对于大角度散射的质子。在研究中模拟的体模中，沿路径包含材料信息（以辐射长度表示）并没有提高准确性。还构建了一个 NN 来预测路径计算中的误差，从而能够筛选出可能对重建图像质量产生负面影响的质子事件。通过参数化大量合成数据，机器学习模型被证明能够将 MC 方法的准确性间接而高效地引入质子跟踪问题。
